INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ðŁĺ

-0.15

soup

-0.14

abilia

-0.14

-0.13

Unity

-0.13

 unpredict

-0.13

 imperson

-0.13

ðŁ

-0.13

unsch

-0.13

 Families

-0.13

POSITIVE LOGITS

0.17

æ³Ĭ

0.16

.googlecode

0.15

åµ

0.14

itorio

0.14

esters

0.14

JPEG

0.14

mono

0.14

 Apartment

0.14

OfString

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.